Instructions to use kandinsky-community/kandinsky-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinsky-community/kandinsky-3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Permission & Ethics Inquiry for Non-Commercial Academic Research (ArtifyAD)
Hello Kandinsky team,
We are fourth-year Computer Science students at the Polytechnic University of the Philippines. Our undergraduate thesis, ArtifyAD, is a binary classifier that labels an artwork as human-made or AI-generated and explains its decision.
We would like to use Kandinsky 3 to generate images that will serve as labelled examples of AI-generated artwork for training and testing our detector. We have read the Apache 2.0 license on this model, and our use is limited to non-commercial academic research. We will not redistribute the generated images or the model weights, the detector does not generate images, and we will cite Kandinsky 3 in our thesis.
Our university's Research Ethics Committee asks us to keep a record of contacting each model owner. A short reply confirming you have no objection would be greatly appreciated.
Thank you for releasing Kandinsky 3.
Sincerely,
Isiah Gabriel Arcos, Lead Researcher
Alron David Mendoza
Drixelle Morales
Denelle Rose Nava
Natasha Julia Yabut
ArtifyAD